空-谱信息与稀疏表示相结合的高光谱遥感影像分类

针对传统的高光谱遥感影像分类中多依赖光谱信息而忽视空间信息以及提取的特征维数高的问题,提出了一种空-谱信息与稀疏表示相结合的分类算法。首先,利用最小噪声分离对原始影像进行降维,在此基础上,对主成分图上局部影像块内的所有像素进行重组,并用排序的方法得到旋转不变的空-谱特征。然后,对空-谱特征进行监督学习得到字典,并将提取的测试样本的空-谱特征编码到字典中以得到测试样本的稀疏表示。最后,使用支持向量机分类器(SVM)对高光谱影像进行分类。3组高光谱数据试验表明,与传统的分类方法比较,本文方法能有效提高分类精度。

Hyperspectral Image Cl assification Based on the Combination of Spati al-spectral Feature and Sparse Representation

In order to avoid the problem of being over‐dependent on high‐dimensional spectral feature in the traditional hyperspectral image cl assification ,a novel approach based on the combination of spati al‐spectral feature and sparse representation is proposed in this paper .Firstly ,we extract the spati al‐spectral feature by reorganizing the local image patch with the first d principal components(PCs) into a vector representation ,followed by a sorting scheme to make the vector invari ant to local image rotation . Secondly ,we learn the dictionary through a supervised method ,and use it to code the features from test samples afterwards .Finally ,we embed the resulting sparse feature coding into the support vector machine (SVM) for hyperspectral image cl assification .Experiments using three hyperspectral data show that the proposed method can effectively improve the cl assification accuracy comparing with traditional cl assifica‐ti on methods .